Nuclear Energy 5.0: New Formation and System Architecture of Nuclear Power Industry in the New IT Era
-
摘要: 本文旨在讨论核能5.0(Nuclear Energy 5.0)的基本概念、体系架构和关键平台技术等问题.首先讨论了核能5.0出现的新智能时代基础,阐述了虚拟数字工业崛起的技术背景.详细叙述了核电工业新形态与体系结构,即平行核能的定义、意义、研究内容、体系架构以及应用领域.接下来讨论了核能5.0中新一代核心技术,包括核能物联网、知识自动化、发展性人工智能、大规模协同演进技术、核能区块链等.最后讨论了核能5.0中在核电系统的具体应用场景与案例,重点是核电工控系统安全评估与核电站数字化仪控系统.Abstract: This paper aims to provide a blueprint for Nuclear Energy 5.0 (NE 5.0), discussing its concept, system architecture and platform technology. We start with a discussion on the social foundation for NE 5.0. Then we illustrate the background of NE 5.0's emergence, which is the rise of virtual digital industry together with its definition, essence, contents, system architecture and application areas. Next we discuss the novel platform technology of NE 5.0 including internet of minds, knowledge automation, developmental artificial intelligence, large-scale co-evolutionary techniques, industrial blockchain, etc. Finally we present two application case studies of NE 5.0 in nuclear power system, i.e., security assessment of nuclear power plant control system and nuclear power plant digital I & C system.
-
Key words:
- Nuclear energy /
- internet of minds /
- knowledge automation /
- parallel system /
- ACP approach /
- blockchain /
- virtual digital industry
-
1. Introduction
Magnetic resonance imaging (MRI) is a crucial medical diagnostic technique which offers clinicians with significant anatomical structure for lack of ionizing. Unfortunately, although it enables highly resolution images and distinguishes depiction of soft tissues, the imaging speed is limited by physical and physiological constraints and increasing scan duration may bring in some physiological motion artifacts [1]. Therefore, it is necessary to seek for a method to decrease the acquisition time. Reducing the number of measurements mandated by Nyquist sampling theory is a way to accelerate the data acquisition at the expense of introducing aliasing artifacts in the reconstructed results. In recent years, compressed sensing (CS) theory, as a promising method, has proposed an essential theoretical foundation for improving data acquisition speed. Particularly, the application of CS to MRI is known as CS-MRI [2]-[6].
The CS theory states that the image which has a sparse representation in certain domain can be recovered from a reduced set of measurements largely below Nyquist sampling rates [2]. The traditional CS-MRI usually utilizes predefined dictionaries [1], [7]-[9], which may fail to sparsely represent the reconstructed images. For instance, Lustig et al. [1] employed the total variation (TV) penalty and the Daubechies wavelet transform for MRI reconstruction. Trzasko et al. [6] proposed a homotopic minimization strategy to reconstruct the MR image. Instead, adaptive dictionary updating in CS-MRI can provide less reconstruction errors due to the dictionary learned from sampled data [10], [11]. Recently, Ravishankar et al. supposed that each image patch has sparse representation, and presented a prominent two-step alternating method named dictionary learning based MRI reconstruction (DLMRI) [12]. The first step is for adaptively learning the dictionary, and the second step is for reconstructing image from undersampled $k$-space data. Numerical experiments have indicated that these data-driven-learning approaches obtained considerable improvements than previous predefined dictionaries-based methods. Liu et al. [13] proposed a gradient based dictionary learning method for image reconstruction (GradDL), which alleviated the drawback of the popular TV regularization by employing dictionary learning technique. Specifically, it firstly trained dictionaries from the horizontal and vertical gradients of the image respectively, and then reconstructed the desired image using the sparse representations of both derivatives. They also extended their ideas to the CT reconstruction and InSAR phase noise filtering [14], [15]. Nevertheless, most of existing methods did not consider the geometrical profit information sufficiently, which may lead to the fine details to be lost.
All the above methods use conventional patch-based sparse representation to reconstruct MR image, it has a fundamental disadvantage that the important spatial structures of the image of interest may be lost due to the subdivision into patches that are independent of each other. To make up for deficiencies of conventional patch-based sparse representation method, Zeiler et al. [16] proposed a convolutional implementation of sparse coding method (CSC). In the convolutional decomposition procedure, the decomposition does not need to divide the entire image into overlapped patches, and can naturally utilize the consistency prior. CSC was first introduced in the context of modeling receptive fields in human vision [17]. Recently, it has been demonstrated that CSC has important applications in a wide range of computer vision problems, like low/mid-level feature learning, low-level reconstruction [18], [19], networks in high-level computer vision or hierarchical structures challenges [16], [20], [21], and in physically-motivated computational imaging problems [22], [23]. In addition, CSC can find applications in many other reconstruction tasks and feature-based methods, including denoising, inpainting, super-resolution and classification [24]-[30].
In this paper, we propose a new formulation of convolutional sparse coding tailored to the problem of MRI reconstruction. Moreover, due to the image gradients are a sparser representation than the image itself and therefore may have sparser representation with the CSC than the pixel-domain image, we learn CSC in gradient domain for better quality and efficient reconstruction. The present method has two benefits. First, we introduce CSC for MRI reconstruction. Second, since the image gradients are usually sparser representation than the image itself, it is demonstrated that the CSC in gradient domain could lead to sparser representation than those using the conventional sparse representation methods in the pixel domain.
The remainder of this paper is organized as follows. Section 2 states the prior work in CS and CSC. The proposed algorithm CSC in gradient domain (GradCSC) that employing the augmented Lagrangian (AL) iterative method is detailed in Section 3. Section 4 demonstrates the performance of the proposed algorithm on examples under a variety of sampling schemes and undersampling factors. Conclusions are given in Section 5.
2. Background
In this section, we first review several classical models for CS-MRI, and then introduce the theory of CSC. The following notational conventions are used throughout the paper. Let denotes an image to be reconstructed, and represents the undersampled Fourier measurements. The partially sampled Fourier encoding matrix ${{F}_{p}}$ $\in$ ${{\mathbb{C}}^{Q\times N}}$ maps $u$ to $f$ such that ${{F}_{p}}u=f$. An MRI reconstruction problem is formulated as the retrieval of the vector $u$ based on the observation $f$ and given the encoding matrix ${{F}_{p}}$.
2.1 CS-MRI
The choice of sparsifying transform is an important question in CS theory. In the past several years, reconstructing unknown image from undersampled measurements was usually formulated as in (1) where assuming the image gradients are sparse
$ \min\limits_{u}\, \left\{ {{\mu }_{1}}{{\left\| u \right\|}_{TV}}+\frac{1}{2}\left\| {{F}_{p}}u-f \right\|_{2}^{2} \right\} $
(1) where is an anisotropic discretization formulation of the TV regularization, $\nabla u={{[u_{x}^{T}, u_{y}^{T}]}^{T}}$, denotes the difference operators in horizontal and vertical directions. This model is very straightforward and has good ability to preserve edges. However, the application of model (1) is limited in terms of reconstruction quality due to most MR images are not all piecewise constant. Yang et al. [31] presented the RecPF method by adding Wavelet transform to improve the issue.
Sparse and redundant representations of image patches based on learned basis has been drawing considerable attention in recent years. Specifically, Ravishankar et al. [12] presented a method named DLMRI to reconstruct MR image from highly undersampled $k$-space data with its objective shown as follows:
$ \min\limits_{u, D, \Gamma }\, \left\{ \sum\limits_{l}{\left\| D{{\alpha }_{l}}-{{R}_{l}}u \right\|_{2}^{2}+\nu {{\left\| {{F}_{p}}u-f \right\|}^{2}}} \right\}\rm{ }\\ {\rm s.t.}\quad {{\left\| {{\alpha }_{l}} \right\|}_{0}}\le {{T}_{0}}~~~ \forall \, l $
(2) where denotes the sparse coefficient matrix of image patches, $R\left( u \right)=[{{R}_{1}}u, {{R}_{2}}u, \ldots, {{R}_{L}}u]$ con-sisting of $L$ signals, ${{\left\|\cdot \right\|}_{0}}$ denotes the ${{l}_{0}}$ quasi-norm which counts the number of non-zero coefficients of the vector and ${{T}_{0}}$ controls the sparsity of the patch representation. Images are reconstructed by the minimization of a linear combination of two terms corresponding to dictionary learning-based sparse representation and least squares data fitting. The first term enforces sparsity of the image patches with respect to an adaptive dictionary, and the second term enforces data fidelity in $k$-space. The method exhibited superior performance compared to those using fixed basis, through learned adaptive transforms from image. Since DL techniques are more effective and efficient in the sparse domain of the image, Liu et al. [13] proposed a model to reconstruct the image by iteratively reconstructing the gradients via dictionary learning and solving for the final image, instead of learning adaptive structure from the image itself. The method is based on the observation that the gradients are sparser than the image itself. Therefore, it possesses sparser representation in the learned dictionary than the pixel-domain.
Although conventional patch-based sparse representation has widely applications, it has some drawbacks. First, it typically assumes that training image patches are independent from each other, hence the consistency of pixels and important spatial structures of the signal of interest may be lost. This assumption typically results in filters are simply translated versions of each other, and generates highly redundant feature representation. Second, due to the nature of the mathematical formulation that a linear combination of learned patches, these traditional patch-based representation approaches may fail to adequately represent high-frequency and high-contrast image features, thus loses some details and textures of the signal, which is important for MR images.
2.2 Convolutional Sparse Coding
Zeiler et al. [16] proposed an alternative to patch-based approaches named CSC, decomposing the image into spatially-invariant convolutional features. CSC is the sum of a set of convolutions of the feature maps by replacing the linear combination of a set of dictionary vectors. Let $X$ be a training set containing $2D$ images with dimension $m$ $\times$ $n$. Let be the $2D$ convolutional filter bank having $K$ filters, where each ${{d}_{k}}$ is a $h\times h$ convolutional kernel. ${{z}_{k}}$ is the sparse feature maps, each of which is the same size as $X$. CSC aims to decompose the input image $X$ into the sparse feature maps ${{z}_{k}}$ convolved with kernels ${{d}_{k}}$ from the filter bank $D$, by solving the following objective function:
$ \underset{d, z}{\mathop{\rm min}}\, \sum\limits_{i=1}^{2}{\frac{1}{2}\left\| X-\sum\limits_{k=1}^{K}{{{d}_{k}}*{{z}_{k}}} \right\|}_{2}^{2}+\beta \sum\limits_{k=1}^{K}{{{\left\| {{z}_{k}} \right\|}_{1}}} \nonumber\\ {\rm s.t.}\quad\left\| {{d}_{k}} \right\|_{2}^{2}\le 1~~~ \forall\, k\in \left\{ 1, \ldots, K \right\} $
(3) where the first and the second terms represent the reconstruction error and the ${{\ell }_{1}}$-norm penalty respectively; $\beta $ is a regularization parameter that controls the relative weight of the sparsity term; $\ast$ is the $2D$ discrete convolution operator; and filters are restricted to have unit energy to avoid trivial solutions. Note that here represents the entrywise matrix norm, the construction of is realized by balancing the reconstruction error and the ${{\ell }_{1}}$-norm penalty.
However, the CSC has led to some difficulties in optimization, Zeile et al. [16] used the continuation method to relax the equality constraints, and employed the conjugate gradient (CG) decent to solve the convolutional least square approximation problem. By considering the property of block circulant with circulant block (BCCB) matrix in the Fourier domain, Bristow et al. [32] presented a fast CSC method. Recently, Wohlberg [33] presented an efficient alternating direction method of multipliers (ADMM) to further improve this method.
3. Convolutional Sparse Coding in Gradient Domain
The image gradients are sparser than the image itself [13], therefore it has sparser representation in the CSC than that in the pixel-domain image. This motivates us to consider the CSC in the gradient domain. It is expected that such learning is more accurate and robust than that from pixel domain. In this work, we propose an algorithm to reconstruct the image by iteratively reconstructing the gradients via CSC and solving for the final image.
3.1 Proposed Model
To reconstruct image from the image gradients, we propose a new model as follows:
$ \begin{align} & \underset{u, d, z}{\mathop{\min }}\, \left\{ \sum\limits_{i=1}^{2}{\frac{1}{2} \left\| {{\nabla }^{(i)}}u-\sum\limits_{k=1}^{K}{{{d}_{k}}*{{z}_{k}}} \right\|}_{2}^{2}\right. \nonumber\\ &\qquad \left.+~\beta \sum\limits_{k=1}^{K}{{{\left\| {{z}_{k}} \right\|}_{1}}} +\frac{{{\nu }_{1}}}{2}{{\left\| {{F}_{p}}u-f \right\|}^{2}}\right\} \nonumber\\ & \, {\rm s.t.}\quad \left\| {{d}_{k}} \right\|_{2}^{2}\le 1~~~ \forall\, k\in \left\{ 1, \ldots, K \right\} \end{align} $
(4) where . The first term and the second term in the cost function (4) capture the sparse prior of the gradient image patches with respect to CSC, and the third term $\| {{F}_{p}}u-f \|_{2}^{2}$ represents the data fidelity term in $k$-space with ${{l}_{2}}$-norm controlling the error. The weight ${{v}_{1}}$ balances the tradeoff between these three terms, and is set as like the DLMRI algorithm does [13], where ${{\lambda }_{1}}$ is a positive constant. $\beta $ is a regularization parameter and controls the relative weight of the sparsity term with respect to the data term. The constraint $\forall\, k\in$ $\{ 1, $ $\ldots, $ can be included in the objective function via an indicator function $ind_{C}( \cdot )$, which is defined on the convex set of the constraint $C=\{ v\ |\| Sv \|_{2}^{2}\le 1 \}$.
In order to better understand the benefit of the CSC in the gradient domain, one demonstration of visual inspection between traditional sparse coded dictionaries and GradCSC filter is shown in Fig. 1. The learned dictionaries by DLMRI and GradDL are depicted in Figs. 1(a) and (b), both of which are learned from the Lumbar spine image in Fig. 2. The learned filters by GradCSC shown in Fig. 1(c) are learned from the dataset in [16]. Compared to the traditional sparse coded dictionaries in Figs. 1(a) and (b), it can be seen from Fig. 1(c) that the convolutional filter in GradCSC shows less redundancy, crisper features, and a larger range of feature orientations.
图 1 One illustration of filters learned. (a) Learned dictionary by DLMRI, (b) Learned dictionary by GradDL, and (c) Learned filter by GradCSC, respectively.Fig. 1 One illustration of filters learned. (a) Learned dictionary by DLMRI, (b) Learned dictionary by GradDL, and (c) Learned filter by GradCSC, respectively.3.2 Algorithm Solver
In the regularization term of (4), the global finite difference operators ${{\nabla }^{(i)}}$ are coupled, hence we resort to the splitting technique to decouple them. Specifically, to find a solution to the model (4), an AL iterative technique is employed and an algorithm called GradCSC is developed. The algorithm alternately updates sparse representations of the image patches, reconstructs the horizontal and vertical gradients, and estimates the original image from both gradients. A full description of the algorithm is given in Algorithm 1.
Algorithm 1. The GradCSC algorithm 1: Initialization: ${{z}_{k}}^{0}=0$, ${{d}_{k}}^{0}=0$, ${{({{b}^{(i)}})}^{0}}=0$, $i=1, 2$; ${{u}^{0}}=F_{p}^{T}f$
2: For $j=1, 2, \ldots $ repeat until a stop-criterion is satisfied
3: ${{({{w}^{(i)}})}^{j+1}}=\ \frac{{{\nu }_{2}}[{{({{b}^{(i)}})}^{j}}+{{({{\nabla }^{(i)}}u)}^{j}}]+\sum\limits_{k=1}^{K}{d_{_{k}}^{j}*z_{_{k}}^{j}}}{2{{\nu }_{2}}+1}, \ \ i=1, 2$
4: Updating $\{{{d}_{k}}^{j+1}, {{z}_{k}}^{j+1}\}$ from difference images ${{({{w}^{(i)}})}^{j+1}}$ by (13), $i=1, 2$
5: Updating $\{ r_{1}^{^{\ell +1}}, r_{2}^{^{\ell +1}}, r_{3}^{^{\ell +1}} \}$ from the coefficients, and the filters by (14)
6: ${{u}^{j+1}}={{F}^{\rm{-}1}}( \frac{F[{{\nu }_{1}}F_{p}^{T}f+{{\nu }_{2}}{{\nabla }^{T}}({{({{w}^{(i)}})}^{j}}^{+1}-{{({{b}^{(i)}})}^{j}})]}{{{\nu }_{1}}FF_{p}^{T}{{F}_{p}}{{F}^{T}}+{{\nu }_{2}}F{{\nabla }^{T}}{{F}^{T}}F\nabla {{F}^{T}}} )$
7: ${{({{b}^{(i)}})}^{j+1}}={{({{b}^{(i)}})}^{j}}+{{({{\nabla }^{(i)}}u)}^{j+1}}-{{({{w}^{(i)}})}^{j+1}}$, $i=1, 2$
8: End
9: Output ${{u}^{j+1}}$Equation (4) can be rewritten as follows by introducing auxiliary variables ${{w}^{(i)}}$, $i=1, 2$.
$ \begin{align} & \nonumber\underset{u, {{w}^{(i)}}, d, z}{\mathop{\min }}\, \left\{ \sum\limits_{i=1}^{2}{\frac{1}{2}\left\| {{w}^{(i)}}-\sum\limits_{k=1}^{K}{{{d}_{k}}*{{z}_{k}}} \right\|_{2}^{2}} \right. \\ &\nonumber \qquad \left. +~\beta \sum\limits_{k=1}^{K}{{{\left\| {{z}_{k}} \right\|}_{1}}} +\frac{{{\nu }_{1}}}{2}{{\left\| {{F}_{p}}u-f \right\|}^{2}}+\sum\limits_{k=1}^{K}{in{{d}_{C}}({{d}_{k}})} \right\} \\ & \, {\rm s.t.}\quad {{w}^{(i)}}={{\nabla }^{(i)}} u~~~\forall \, i \end{align} $
(5) then, by employing the AL technique and denoting , and , it yields a sequence of constrained subproblems as follows:
$ \begin{align} & \left\{{{u}^{j+1}}, {{w}^{j+1}}, {{d}^{j+1}}, {{z}^{j+1}}\right\} \nonumber\\ & \qquad={\arg} \underset{u, {{w}^{(i)}}, d, z}{\mathop{\rm min}}\, \sum\limits_{i=1}^{2}{\frac{1}{2}\left\| {{w}^{(i)}}-\sum\limits_{k=1}^{K}{{{d}_{k}}* {{z}_{k}}} \right\|_{2}^{2}}\nonumber\\ &\qquad\quad+\frac{{{\nu }_{1}}}{2}\left\| {{F}_{p}}u-f \right\|_{2}^{2} +\beta \sum\limits_{k=1}^{K}{{{\left\| {{z}_{k}} \right\|}_{p}}}+ \sum\limits_{k=1}^{K}{in{{d}_{C}}({{d}_{k}})}\nonumber\\ &\qquad\quad+\frac{{{\nu }_{2}}}{2}\left\| {{\left({{b}^{(i)}}\right)}^{j}}+\nabla u-{{w}^{(i)}} \right\|_{2}^{2} \end{align} $
(6) $ {{\left({{b}^{(i)}}\right)}^{j+1}}={{\left({{b}^{(i)}}\right)}^{j}}+\nabla {{u}^{j+1}}-{{\left({{w}^{(i)}}\right)}^{j+1}} $
(7) where ${{\nu }_{2}}$ denotes the positive penalty parameter. The ADMM can be used to address the minimization of (6) with respect to $u$, $w$, $z$, and $d$. This technique carries out approximation via alternating minimization with respect to one variable while keeping other variables fixed.
1) Updating the Solution $u$: At the $j$th iteration, we assume $w$, $z$, and $d$ to be fixed with their values denoted as ${{w}^{j}}$, ${{z}^{j}}$, and ${{d}^{j}}$, respectively. Eliminating the constant variables, the objective function for updating $u$ is given as
$ \begin{align} \nonumber{{u}^{j+1}}=\, & \arg \underset{u}{\mathop{\min }}\, \bigg\{ {{\nu }_{1}}\left\| {{F}_{p}}u-f \right\|_{2}^{2} \\ & +~{{\nu }_{2}}\left\| {{({{b}^{(i)}})}^{j}}+\nabla u-{{({{w}^{(i)}})}^{j}} \right\|_{2}^{2} \bigg\}. \end{align} $
(8) Recognizing that (8) is a simple least squares problem admitting an analytical solution. The least squares solution satisfies the normal equation
$ \left( {{\nu }_{1}}F_{p}^{T}{{F}_{p}}+{{\nu }_{2}}{{\nabla }^{T}}\nabla \right){{u}^{j+1}}={{\nu }_{1}}F_{p}^{T}f+{{\nu }_{2}}{{\nabla }^{T}}({{w}^{j}}-{{b}^{j}}). $
(9) However, directly solving the equation can be tedious due to (9) has a high computation complexity ($O({{P}^{3}})$). Fortunately, we can use the convolution theorem of Fourier transform to obtain the solution:
$ {{u}^{j+1}}={{F}^{-1}}\left( \frac{F\left[{{\nu }_{1}}F_{p}^{T}f+{{\nu }_{2}}{{\nabla }^{T}}({{w}^{j}}-{{b}^{j}})\right]}{{{\nu }_{1}}FF_{p}^{T}{{F}_{p}}{{F}^{T}}+{{\nu }_{2}}F{{\nabla }^{T}}{{F}^{T}}F\nabla {{F}^{T}}} \right) $
(10) similarly as described in DLMRI and GradDL method [12], the matrix $FF_{p}^{T}{{F}_{p}}{{F}^{T}}$ is a diagonal matrix consisting of ones and zeroes corresponding to the sampled location in $k$-space.
2) Updating the Gradient Image Variables ${w}^{(i)}$, $i$ = 1, 2: The minimization in (6) with respect to ${{w}^{(1)}}$ and ${{w}^{(2)}}$ are decoupled, and then can be solved separately. It yields:
$ \begin{align} \nonumber{{({{w}^{(i)}})}^{j+1}}=&\ \arg ~\underset{{{w}^{(i)}}}{\mathop{\min }}\, \Bigg\{ \frac{1}{2}\left\| \sum\limits_{k=1}^{K}{d_{_{k}}^{j}*z_{_{k}}^{j}}-{{w}^{(i)}} \right\|_{2}^{2} \\ & \ +\frac{{{\nu }_{2}}}{2}\left\| {{\left({{b}^{(i)}}\right)}^{j}}+{{ \left({{\nabla }^{(i)}}u\right)}^{j+1}}-{{w}^{(i)}} \right\|_{2}^{2} \Bigg\}. \end{align} $
(11) The least squares solution satisfies the normal equation, and the solution of (11) is as follow:
$ {{\left({{w}^{(i)}}\right)}^{j+1}}=\frac{{{\nu }_{2}}\left[{{\left({{b}^{(i)}}\right)}^{j}}+{{\left({{\nabla }^{(i)}}u\right)}^{j+1}}\right]+\sum\limits_{k=1}^{K}{d_{_{k}}^{j}*z_{_{k}}^{j}}}{{{\nu }_{2}}+1}. $
(12) 3) Updating the Coefficients $z$, and the Filters $d$: The minimization (6) with respect to CSC and coefficient variables of the gradient image in horizontal and vertical yields:
$ \begin{align} &\underset{{{d}^{j+1}}, {{z}^{j+1}}}{\mathop{\min }}\, \frac{1}{2}\left\| {{w}^{(i)}}-\sum\limits_{k=1}^{K}{{{d}_{k}}*{{z}_{k}}} \right\|_{2}^{2}\nonumber\\ &\qquad +\beta \sum\limits_{k=1}^{K}{{{\left\| {{z}_{k}} \right\|}_{1}}}+\sum\limits_{k=1}^{K}{in{{d}_{C}}({{d}_{k}})}. \end{align} $
(13) The problem in (13) can be solved by employing an AL algorithm like mentioned above, (13) needs to introduce auxiliary variables ${{r}_{1}}=\sum_{k=1}^{K}d_{_{k}}^{j+1}\ast z_{_{k}}^{j+1}$, ${{r}_{2}}={{d}^{j+1}}$, ${{r}_{3}}$ $=$ $z_{_{k}}^{j+1}$, it solves:
$ \begin{align} & \nonumber\left\{ d_{k}^{j+1, \ell +1}, z_{k}^{j+1, \ell +1}, r_{1}^ {^{\ell +1}}, r_{2}^{^{\ell +1}}, r_{3}^{^{\ell +1}} \right\} \\ \nonumber&\qquad ={\rm arg }\ \underset{{{d}^{j+1}}, {{z}^{j+1}}, {{r}_{1}}, {{r}_{2}}, {{r}_{3}}}{\mathop{\min }}\, \Bigg\{ \frac{1}{2}\left\| {{\left({{w}^{(i)}}\right)}^ {j+1}}-{{r}_{1}} \right\|_{2}^{2} \\ \nonumber&\qquad\quad +\sum\limits_{k=1}^{ K}{in{{d}_{C}}({{r}_{2, k}})}\ +\beta \sum\limits_{k=1}^{K}{ {{\left\| {{r}_{3, k}} \right\|}_{1}}}\\ \nonumber&\qquad\quad +\frac{{{\mu }_{1}}}{2}\left\| {{r}_{1}}-\sum\limits_{k=1}^{K}{d_{_{k}}^{j+1}*z_{_{k}}^{j+1}}+\lambda _{_{1}}^{j} \right\|_{2}^{2}\ \\ &\qquad\quad +\frac{{{\mu }_{2}}}{2}\left\| {{r}_{2}}-d_{_{k}}^{j+1}+ \lambda _{_{2}}^{j} \right\|_{2}^{2}+\frac{{{\mu }_{3}}}{2}\left\| {{r}_{3}}-z_{_{k}}^{j+1}+\lambda _{3}^{\ell } \right\|_{2}^{2} \Bigg\} \end{align} $
(14) at the $\ell$th iteration for ${{d}^{j+1, \ell +1}}$, , $r_{^{1}}^{\ell +1}$, $r_{^{2}}^{\ell +1}$, , then updates the multipliers ${{\lambda }_{1}}$, and ${{\lambda }_{3}}$ by the formula
$ \begin{align} &\nonumber \lambda _{_{1}}^{\ell +1}=\lambda _{_{1}}^{\ell }+r_{_{1}}^{\ell +1}-\sum\limits_{k=1}^{K}{d_{_{k}}^{j+1, \ell +1}*z_{_{k}}^{j+1, \ell +1}} \\ \nonumber& \lambda _{2}^{\ell +1}=\lambda _{_{2}}^{\ell }+r_{_{2}}^{\ell +1}-d_{_{k}}^{j+1, \ell +1} \\ & \lambda _{3}^{\ell +1}=\lambda _{3}^{\ell }+r_{3}^{\ell +1}-d_{_{k}}^{j+1, \ell +1}. \end{align} $
(15) ADMM is chosen to solve the (14). The corresponding five subproblems can be solved as follows:
$ \begin{align} \nonumber d_{k}^{j+1, \ell +1}=&\ {{\left( {{\left(z_{k}^{j+1, \ell }\right)}^{T}}z_{k}^{j+1, \ell }+\frac{{{\mu }_{2}}}{{{\mu }_{1}}}I \right)}^{-1}} \\ \nonumber &\ \times\left( {{\left(z_{k}^{j+1, \ell }\right)}^{T}}\left( r_{_{1}}^{\ell }+\lambda _{_{1}}^{\ell } \right)+\frac{{{\mu }_{2}}}{{{\mu }_{1}}}\left( r_{2}^{\ell }+\lambda _{_{2}}^{\ell } \right) \right) \\ \end{align} $
(16) $ \begin{align} \nonumber z_{k}^{j+1, \ell +1}=&\ {{\left( {{\left(d_{k}^{j+1, \ell +1}\right)}^{T}}d_{k}^{j+1, \ell +1}+\frac{{{\mu }_{4}}}{{{\mu }_{3}}}I \right)}^{-1}} \\ &\ \times\left( {{\left(d_{k}^{j+1, \ell +1}\right)}^{T}}\left(r_{_{3}}^{\ell }+\lambda _{_{3}}^{\ell }\right) +\frac{{{\mu }_{4}}}{{{\mu }_{3}}}\left(r_{_{4}}^{\ell }+\lambda _{_{4}}^{\ell }\right) \right) \end{align} $
(17) $ \begin{align} r_{1}^{^{\ell +1}}=&\ \left({{\mu }_{1}}+1\right){{I}^{-1}}\nonumber\\ &\ \times\left[\left({{\mu }_{1}}\sum\limits_{k=1}^{K}{z_{_{k}}^{j+1, \ell }*d_{_{k}}^{j+1, \ell +1}}-\lambda _{_{1}}^{\ell }\right)+{{\left({{w}^{(i)}}\right)}^{j+1}}\right]\\ \end{align} $
(18) $ \begin{align} r_{2, k}^{^{l+1}}=&\ \begin{cases} \frac{d_{_{k}}^{j+1, \ell +1}-\lambda _{_{2}}^{\ell }}{{{\left\| d_{_{k}}^{j+1}-\lambda _{_{2}}^{j} \right\|}_{2}}}, &d_{_{k}}^{j+1, \ell +1}-\lambda _{_{2}}^{\ell }\ge 1\\[4mm] d_{_{k}}^{j+1, \ell +1}-\lambda _{_{2}}^{\ell }, & {\rm else} \end{cases} \end{align} $
(19) where .
$ \begin{align} r_{3}^{^{\ell +1}}=&\ \max \left\{ 1-\frac{\beta }{{{\mu }_{3}}{{\left\| z_{_{k}}^{j+1, \ell +1}-\lambda _{3}^{\ell } \right\|}_{2}}}, 0 \right\}\nonumber\\&\ \circ \left( z_{_{k}}^{j+1, \ell +1}-\lambda _{3}^{\ell } \right) \end{align} $
(20) where $\circ $ represents the point-wise product function and the operation is implemented by component-wise manner.
4. Experimental Results
In this section, we evaluate the performance of proposed method at a variety of sampling schemes and undersampling factors. The sampling schemes employed in the experiments contain the 2D random sampling, pseudo radial sampling, and Cartesian sampling with random phase encoding (1D random). The size of images we use in the synthetic experiments are $512\times 512$. The CS data acquisition was simulated by subsampling the 2D discrete Fourier transform of the MR images (except the test with real acquired data) in the light of many prior work on CS-MRI approaches, . In order to find the sparse feature map ${{z}_{k}}$, we use a fixed filter $D$ which is trained from reference MR images. We find that learning $K=100$ filters of size $11\times 11$ pixels fulfills these conditions for our data and works well for all the images tested. In the experiment, the proposed method GradCSC is compared with the leading DLMRI [12] and GradDL [13] methods that have shown the substantially outperform other CS-MRI methods. In addition, we use the peak signal-to-noise ratio (PSNR) and high-frequency error norm (HFEN) [20] to evaluate the quality of reconstruction. All of these algorithms are implemented in MATLAB 7.1 on a PC equipped with AMD 2.31 GHz CPU and 3 GByte RAM.
4.1 Experiments Under Different Undersampling Factors
In this subsection, we evaluate the performance of GradCSC under different undersampling factors with same sampling scheme. Fig. 2 illustrates the reconstruction results at a range of undersampling factors with 2.5, 4, 6, 8, 10 and 20. We added the zero-mean complex white Gaussian noise with $\sigma =10.2$ in the 2D random sampled $k$-space. The PSNR and HFEN values for DLMRI, GradDL and GradCSC at various undersampling factors are presented in Figs. 2(b) and (c), additionally the PSNR values are listed in Table Ⅰ. For the subjective comparison, the construction results and magnitude image of the reconstruction error provided by the three methods at 8-fold undersampling are presented in Figs. 2(d), (e), (f) and (g), (h), (i), respectively. In this case, it can be seen that the image reconstructed by the DLMRI method (shown in Fig. 2(d)) is blurred and loses some textures. Although both GradDL and GradCSC present excellent performances on suppressing aliasing artifacts, our GradCSC provides a better reconstruction of object edges (such as the spine) and preserves finer texture information (such as the bottom-right of the reconstruction). Such difference in reconstruction quality is particularly clear in the image errors shown in Figs. 2(g), (h) and (i). In general, our proposed method provides greater intensity fidelity to the image reconstructed from the full data.
表 Ⅰ Reconstruction PSNR Values at Different Undersampling Factors With the Same 2D Random Sampling TrajectoriesTable Ⅰ Reconstruction PSNR Values at Different Undersampling Factors With the Same 2D Random Sampling TrajectoriesUndersampling factors 2.5-fold 4-fold 6-fold 8-fold 10-fold 20-fold DLMRI 35.92 35.19 31.26 30.76 30.13 26.39 GradDL 38.26 38.20 34.35 32.89 31.81 27.90 GradCSC 37.39 37.53 35.23 35.45 34.62 30.54 4.2 Impact of Undersampling Schemes
In this subsection, we evaluate the performance of GradCSC at various sampling schemes. The results are presented in Fig. 3 which reconstructed an axial T2-weighted brain image at 8-fold undersampling factors by applying three different sampling schemes, including 2D random sampling, 1D Cartesian sampling, and pseudo radial sampling. The PSNR and HFEN indexes versus iterative number for method DLMRI, GradDL and GradCSC are plotted in Figs. 3(b) and (c). Particularly, we present the reconstructions of DLMRI, GradDL and GradCSC with 2D random sampling in Figs. 3(d), (e), and (f), respectively. In order to facilitate the observation, the difference image between reconstruction results are shown in Figs. 3(g), (h), and (i). As can be expected, the convolution operator enables CSC outperform DLMRI and GradDL methods for most of specified undersampling ratios and trajectories. This exhibits the benefits of employing the convolutional filter for sparse coding. In particular, in Fig. 3(d), (e), and (f) the skeletons in the top half part of the GradCSC reconstruction appear less obscured than those in the DLMRI and GradDL results. the proposed method GradCSC reconstructs the images more accurately with larger PSNR and lower HFEN values than the GradDL approach. Particularly when sampled at 2D random trajectory, our method GradCSC outperforms others with a remarkable improvement from 0.7 dB to 5.8 dB.
4.3 Performances at Different Noise Levels
We also conduct experiments to investigate the sensitivity of GradCSC to different levels of complex white Gaussian noise. DLMRI, GradDL and GradCSC are applied to reconstruct a noncontrast MRA of the circle of Willis under pseudo radial sampling at 6.67-fold acceleration. Fig. 4 presents the reconstruction results of three methods at different levels of complex white Gaussian noise, which are added to the $k$-space samples. Fig. 4(c) presents the PSNRs of DLMRI, GradDL and GradCSC at a sequence of different standard deviations (0, 2, 5, 8, 10, 12, 15). Reconstruction results with noise 5 are shown in Figs. 4(d), (e), and (f). The PSNRs gained by DLMRI and GradDL are 27.03 dB and 29.78 dB, while the GradCSC method achieves 30.45 dB. Obviously, the reconstruction obtained by GradCSC is clearer than those by DLMRI and GradDL. It can be observed that our GradCSC method can reconstruct the images more precisely than DLMRI and GradDL, in terms of extracting more structural and detail information from gradient domain. The corresponding error magnitudes of the reconstruction are displayed in Figs. 4(g), (h), and (i). It reveals that our method provides a more accurate reconstruction of image contrast and sharper anatomical depiction in noisy case.
5. Conclusion
In this work, a novel CSC method in gradient domain for MR image reconstruction was proposed. The important spatial structures of the signal were preserved by convolutional sparse coding. For the new derived model, we utilized the AL method to implement the algorithm in a few number of iterations. A variety of experimental results demonstrated the superior performance of the method under various sampling trajectories and $k$-space acceleration factors. The proposed method can produce highly accurate reconstructions for severely undersampled factors. It provided superior performance in both noiseless and noisy cases. The presented framework will be extended to parallel imaging applications in the future work.
-
-
[1] 张廷克, 李闽榕, 潘启龙.中国核能发展报告(2018).北京:社会科学文献出版社, 2018. [2] 卡尔·波普尔.客观知识:一个进化论的研究.上海:上海译文出版社, 1972.Popper K R. Objective Knowledge:An Evolutionary Approach. Shanghai:Shanghai Translation Publishing House, 1972. [3] Jaspers K. The Origin and Goal of History. Munich:Piper Verlag GmbH, 1949. [4] 库尔特·哥德尔. 〈数学原理〉及有关系统中的形式不可判定命题. 1931.Gödel K. On Formally Undecidable Propositions of Principia Mathematica and Related Systems(Ⅰ). 1931. [5] 王飞跃.软件定义的系统与知识自动化:从牛顿到默顿的平行升华.自动化学报, 2015, 41(1):1-8 http://www.aas.net.cn/CN/abstract/abstract18578.shtmlWang Fei-Yue. Software-defined systems and knowledge automation:a parallel paradigm shift from Newton to Merton. Acta Automatica Sinica, 2015, 41(1):1-8 http://www.aas.net.cn/CN/abstract/abstract18578.shtml [6] Wang F Y. The emergence of intelligent enterprises:from CPS to CPSS. IEEE Intelligent Systems, 2010, 25(4):85-88 doi: 10.1109/MIS.2010.104 [7] 王飞跃, 杨坚, 韩双双, 杨柳青, 程翔.基于平行系统理论的平行网络架构.指挥与控制学报, 2016, 2(1):71-77 https://www.researchgate.net/profile/Fei_Yue_Wang/publication/317328968_The_Framework_of_Parallel_Network_Based_on_the_Parallel_System_Theory/links/5932737845851553b6aabedf/The-Framework-of-Parallel-Network-Based-on-the-Parallel-System-Theory.pdfWang Fei-Yue, Yang Jian, Han Shuang-Shuang, Yang Liu-Qing, Cheng Xiang. The framework of parallel network based on the parallel system theory. Journal of Command and Control, 2016, 2(1):71-77 https://www.researchgate.net/profile/Fei_Yue_Wang/publication/317328968_The_Framework_of_Parallel_Network_Based_on_the_Parallel_System_Theory/links/5932737845851553b6aabedf/The-Framework-of-Parallel-Network-Based-on-the-Parallel-System-Theory.pdf [8] 王飞跃. X5. 0: 平行时代的平行智能体系. 新时代智能论坛, 2015. https://www.researchgate.net/publication/317328952_X50pingxingshidaidepingxingzhinengtixiWANG Fei-Yue. X5. 0: Parallel Intelligence System in Parallel ERA. The New Intelligence Age Forum. 2015. https://www.researchgate.net/publication/317328952_X50pingxingshidaidepingxingzhinengtixi [9] 王飞跃.平行系统方法与复杂系统的管理和控制.控制与决策, 2004, 19(5):485-489 http://mall.cnki.net/magazine/Article/KZYC200405001.htmWang Fei-Yue. Parallel system methods for management and control of complex systems. Control and Decision, 2004, 19(5):485-489 http://mall.cnki.net/magazine/Article/KZYC200405001.htm [10] 王飞跃.平行控制:数据驱动的计算控制方法.自动化学报, 2013, 39(4):293-302 http://www.aas.net.cn/CN/abstract/abstract17915.shtmlWang Fei-Yue. Parallel control:a method for data-driven and computational control. Acta Automatica Sinica, 2013, 39(4):293-302 http://www.aas.net.cn/CN/abstract/abstract17915.shtml [11] 宁滨, 王飞跃, 董海荣, 文丁.高速铁路平行控制与管理系统研究框架.复杂系统与复杂性科学, 2010, 7(4):11-21 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=fzxtyfzxkx201004002Ning Bin, Wang Fei-yue, Dong Hai-rong, Wen Ding. Framework of parallel control and management for high-speed railway systems. Complex Systems And Complexity Science, 2010, 7(4):11-21 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=fzxtyfzxkx201004002 [12] Glaessgen E H, Stargel D S. The digital twin paradigm for future NASA and U. S. air force vehicles. In: Proceedings of the 53rd AIAA/ASME/ASCE/AHS/ASC Structures, Structural Dynamics and Materials Conference. Honolulu, Hawaii, USA: AIAA, 2012. doi: 10.2514/6.2012-1818 [13] Weber A. GE 'predix' the future of manufacturing. Assembly, 2017, 60(3):GE70-GE76 https://www.ptc.com/en/news/2016/ptc-and-ge-digital-to-expand-strategic-alliance [14] 熊刚, 董西松, 王兆魁, 王飞跃. 平行控制与管理的研究及应用进展综述. 中国空天安全会议, 2017 http://cpfd.cnki.com.cn/Article/CPFDTOTAL-ZHKT201708001090.htmXiong Gang, Dong Xi-Song, Wang Zhao-Kui, Wang Fei-Yue. Research and Application Review of Parallel Control and Management. Chinese Aerospace Safety Symposium, 2017 http://cpfd.cnki.com.cn/Article/CPFDTOTAL-ZHKT201708001090.htm [15] 王飞跃. 复杂系统的控制与管理机制研究及其应用. 见: 中国科学院院长基金特别支持项目立项书. 北京, 2005.Wang Fei-Yue. New mechanisms for control and management of complex systems: research and development. In: Project to the Presidents Foundation for Special Projects, Chinese Academy of Sciences. Beijing, China, 2005. [16] Wang F Y, Wang X, Li L X, Li L. Steps toward parallel intelligence. IEEE/CAA Journal of Automatica Sinica, 2016, 3(4):345-348 doi: 10.1109/JAS.2016.7510067 [17] 李力, 林懿伦, 曹东璞, 郑南宁, 王飞跃.平行学习——机器学习的一个新型理论框架.自动化学报, 2017, 43(1):1-8 http://www.aas.net.cn/CN/abstract/abstract18984.shtmlLi Li, Lin Yi-Lun, Cao Dong-Pu, Zheng Nan-Ning, Wang Fei-Yue. Parallel learning:a new framework for machine learning. Acta Automatica Sinica, 2017, 43(1):1-8 http://www.aas.net.cn/CN/abstract/abstract18984.shtml [18] Wang F Y, Zhang J, Wei Q L, Zheng X H, Li L. PDP:parallel dynamic programming. IEEE/CAA Journal of Automatica Sinica, 2017, 4(1):1-5 doi: 10.1109/JAS.2017.7510310 [19] 王飞跃, 王晓, 袁勇, 王涛, 林懿伦.社会计算与计算社会:智慧社会的基础与必然.科学通报, 2015, 60(5-6):460-469 http://mall.cnki.net/magazine/Article/KXTB2015Z1008.htmWang Fei-Yue, Wang Xiao, Yuan Yong, Wang Tao, Lin Yi-Lun. Social computing and computational societies:the foundation and consequence of smart societies. Chinese Science Bulletin, 2015, 60(5-6):460-469 http://mall.cnki.net/magazine/Article/KXTB2015Z1008.htm [20] Wang F Y, Wong P K. Intelligent systems and technology for integrative and predictive medicine:an ACP approach. ACM Transactions on Intelligent Systems and Technology, 2013, 4(2):Article No.32 http://europepmc.org/abstract/med/24883228 [21] Wang F Y. Toward a paradigm shift in social computing:the ACP approach. IEEE Intelligent Systems, 2007, 22(5):65-67 doi: 10.1109/MIS.2007.4338496 [22] Wang F Y. Parallel control and management for intelligent transportation systems:concepts, architectures, and applications. IEEE Transactions on Intelligent Transportation Systems, 2010, 11(3):630-638 doi: 10.1109/TITS.2010.2060218 [23] 王飞跃, 李晓晨, 毛文吉, 王涛.社会计算的基本方法与应用.杭州:浙江大学出版社, 2012.Wang Fei-Yue, Li Xiao-Chen, Mao Wen-Ji, Wang Tao. Social Computing:Methods and Applications. Hangzhou:Zhejiang University Press, 2012. [24] 王飞跃. 社会能源与平行能源系统: 迈向能源5. 0的时代. 见: 分布式能源专业委员会筹备会及IEEE ITSS北京分会. 北京: 北方工业大学, 2015.Wang Fei-Yue. Social energy and parallel energy systems: towards the age of energy 5. 0. In: Workshop on Distributed Energy Systems and Annual Symposium of IEEE ITSS Beijing Chapter. Beijing, China: North China University of Technology, 2015. [25] 王飞跃, 赵杰, 伦淑娴.人工电力系统与复杂大电网的运营和管理.南方电网技术, 2008, 2(3):1-6 http://www.cqvip.com/QK/88821X/200803/27981370.htmlWang Fei-Yue, Zhao Jie, Lun Shu-Xian. Artificial power systems for the operation and management of complex power grids. Southern Power System Technology, 2008, 2(3):1-6 http://www.cqvip.com/QK/88821X/200803/27981370.html [26] 赵俊华, 文福拴, 薛禹胜, 董朝阳.电力信息物理融合系统的建模分析与控制研究框架.电力系统自动化, 2011, 35(16):1-8 http://mall.cnki.net/magazine/Article/DLXT201116000.htmZhao Jun-Hua, Wen Fu-Shuan, Xue Yu-Sheng, Dong Zhao-Yang. Modeling analysis and control research framework of cyber physical power systems. Automation of Electric Power Systems, 2011, 35(16):1-8 http://mall.cnki.net/magazine/Article/DLXT201116000.htm [27] 赵俊华, 文福拴, 薛禹胜, 李雪, 董朝阳.电力CPS的架构及其实现技术与挑战.电力系统自动化, 2010, 34(16):1-7 http://mall.cnki.net/magazine/article/DLXT201016000.htmZhao Jun-Hua, Wen Fu-Shuan, Xue Yu-Sheng, Li Xue, Dong Zhao-Yang. Cyber physical power systems:architecture, implementation techniques and challenges. Automation of Electric Power Systems, 2010, 34(16):1-7 http://mall.cnki.net/magazine/article/DLXT201016000.htm [28] Ilic M D, Xie L, Khan U A, Moura J M F. Modeling of future cyber-physical energy systems for distributed sensing and control. IEEE Transactions on Systems, Man, and Cybernetics. Part A:Systems and Humans, 2010, 40(4):825-838 doi: 10.1109/TSMCA.2010.2048026 [29] Xie L, Ilic M D. Module-based modeling of cyber-physical power systems. In: Proceedings of the 28th International Conference on Distributed Computing Systems Workshops. Beijing, China: IEEE, 2008. 513-518 http://dl.acm.org/citation.cfm?id=1439719 [30] McMillin B. Complexities of information security in cyber-physical power systems. In: Proceedings of the 2009 IEEE/PES Power Systems Conference and Exposition. Seattle, WA, USA: IEEE, 2009. 1-2 http://ieeexplore.ieee.org/document/4840093/ [31] Singh C, Sprintson A. Reliability assurance of cyber-physical power systems. In: Proceedings of the 2010 IEEE Power and Energy Society General Meeting. Minneapolis, MN, USA: IEEE, 2010. 1-6 http://www.researchgate.net/publication/224179251_Reliability_assurance_of_cyber-physical_power_systems [32] 邓建玲, 王飞跃, 陈耀斌, 赵向阳.从工业4.0到能源5.0:智能能源系统的概念、内涵及体系框架.自动化学报, 2015, 41(12):2003-2016 http://www.aas.net.cn/CN/abstract/abstract18774.shtmlDeng Jian-Ling, Wang Fei-Yue, Chen Yao-Bin, Zhao Xiang-Yang. From industries 4.0 to energy 5.0:concept and framework of intelligent energy systems. Acta Automatica Sinica, 2015, 41(12):2003-2016 http://www.aas.net.cn/CN/abstract/abstract18774.shtml [33] 王飞跃.指控5.0:平行时代的智能指挥与控制体系.指挥与控制学报, 2015, 1(1):107-120 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=zhykzxb201501018Wang Fei-Yue. CC 5.0:intelligent command and control systems in the parallel age. Journal of Command and Control, 2015, 1(1):107-120 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=zhykzxb201501018 [34] 江泽民.对中国能源问题的思考.上海交通大学学报, 2008, 42(3):345-359 http://mall.cnki.net/magazine/Article/SHJT200803002.htmJiang Ze-Min. Reflections on energy issues in China. Journal of Shanghai Jiaotong University, 2008, 42(3):345-359 http://mall.cnki.net/magazine/Article/SHJT200803002.htm [35] 张力. 概率安全评价中人因可靠性分析技术研究[博士学位论文], 湖南大学, 中国, 2004 http://cdmd.cnki.com.cn/Article/CDMD-10532-2005040162.htmZhang Li. The Research on Human Reliability Analysis Technique in Probabilistic Safety Assessment[Ph. D. dissertation], Hu'nan University, China, 2004 http://cdmd.cnki.com.cn/Article/CDMD-10532-2005040162.htm [36] 薛禹胜, 肖世杰.综合防御高风险的小概率事件:对日本相继天灾引发大停电及核泄漏事件的思考.电力系统自动化, 2011, 35(8):1-11 http://industry.wanfangdata.com.cn/dl/Detail/Periodical?id=Periodical_dlxtzdh201108001Xue Yu-Sheng, Xiao Shi-Jie. Comprehensively defending high risk events with low probability. Automation of Electric Power Systems, 2011, 35(8):1-11 http://industry.wanfangdata.com.cn/dl/Detail/Periodical?id=Periodical_dlxtzdh201108001 [37] 荆春宁, 赵科, 张力友, 李辉, 王诚诚, 钱怡洁, 等. "华龙一号"的设计理念与总体技术特征.中国核电, 2017, 10(4):463-467 http://www.cqvip.com/QK/89379X/201302/46329432.htmlJing Chun-Ning, Zhao Ke, Zhang Li-You, Li Hui, Wang Cheng-Cheng, Qian Yi-Jie, et al. The design philosophy and general technical features of HPR1000. China Nuclear Power, 2017, 10(4):463-467 http://www.cqvip.com/QK/89379X/201302/46329432.html [38] 朱正威, 王琼, 吕书鹏.多元主体风险感知与社会冲突差异性研究——基于Z核电项目的实证考察.公共管理学报, 2016, (2):97-106 http://www.cqvip.com/QK/87267X/201602/668566259.htmlZhu Zheng-Wei, Wang Qiong, Lv Shu-Peng. Research on differences of multiple stakeholders' risk perception and social conflict——Empirical investigation of Z nuclear power project. Journal of Public Management, 2016, (2):97-106 http://www.cqvip.com/QK/87267X/201602/668566259.html [39] 李鹏程, 张力, 戴立操, 邹衍华, 青涛, 胡鸿等.核电厂数字化主控室操纵员的情景意识可靠性模型.系统工程理论与实践, 2016, 36(1):243-252 doi: 10.12011/1000-6788(2016)01-0243-10Li Peng-Cheng, Zhang Li, Dai Li-Cao, Zou Yan-Hua, Qing Tao, Hu Hong, et al. Operator's situation awareness reliability model in digital main control rooms of nuclear power plants. Systems Engineering——Theory and Practice, 2016, 36(1):243-252 doi: 10.12011/1000-6788(2016)01-0243-10 [40] 王晓磊, 吕大刚.核电厂地震概率风险评估研究综述.土木工程学报, 2016, 49(11):52-68 http://www.cnki.com.cn/Article/CJFDTotal-DEFE201206003.htmWang Xiao-Lei, Lv Da-Gang. Review of seismic probability risk assessment of nuclear power plants. China Civil Engineering Journal, 2016, 49(11):52-68 http://www.cnki.com.cn/Article/CJFDTotal-DEFE201206003.htm [41] 苏罡.中国核能科技"三步走"发展战略的思考.科技导报, 2016, 34(15):33-41 http://blog.sciencenet.cn/blog-336909-1005353.htmlSu Gang. The "three steps development strategy" of China nuclear power science and technology. Science & Technology Review, 2016, 34(15):33-41 http://blog.sciencenet.cn/blog-336909-1005353.html [42] 王飞跃, 张俊.智联网:概念、问题和平台.自动化学报, 2017, 43(12):2061-2070 http://www.aas.net.cn/CN/abstract/abstract19181.shtmlWang Fei-Yue, Zhang Jun. Internet of minds:the concept, issues and platforms. Acta Automatica Sinica, 2017, 43(12):2061-2070 http://www.aas.net.cn/CN/abstract/abstract19181.shtml [43] 程乐峰, 余涛, 张孝顺, 殷林飞, 瞿凯平.信息-物理-社会融合的智慧能源调度机器人及其知识自动化:框架、技术与挑战.中国电机工程学报, 2018, 38(1):25-40 http://www.cnki.com.cn/Article/CJFDTotal-DLXT201415001.htmCheng Le-Feng, Yu Tao, Zhang Xiao-Shun, Yin Lin-Fei, Qu Kai-Ping. Cyber-physical-social systems based smart energy robotic dispatcher and its knowledge automation:framework, techniques and challenges. Proceedings of the CSEE, 2018, 38(1):25-40 http://www.cnki.com.cn/Article/CJFDTotal-DLXT201415001.htm [44] Wang F Y, Zhang J J, Wang X. Parallel intelligence:toward lifelong and eternal developmental AI and learning in cyber-physical-social spaces. Frontiers of Computer Science, 2018, 12(3):401-405 doi: 10.1007/s11704-018-7903-5 [45] 袁勇, 王飞跃.区块链技术发展现状与展望.自动化学报, 2016, 42(4):481-494 http://www.aas.net.cn/CN/abstract/abstract18837.shtmlYuan Yong, Wang Fei-Yue. Blockchain:the state of the art and future trends. Acta Automatica Sinica, 2016, 42(4):481-494 http://www.aas.net.cn/CN/abstract/abstract18837.shtml [46] 袁勇, 周涛, 周傲英, 段永朝, 王飞跃.区块链技术:从数据智能到知识自动化.自动化学报, 2017, 43(9):1485-1490 http://www.aas.net.cn/CN/abstract/abstract19125.shtmlYuan Yong, Zhou Tao, Zhou Ao-Ying, Duan Yong-Chao, Wang Fei-Yue. Blockchain technology:from data intelligence to knowledge automation. Acta Automatica Sinica, 2017, 43(9):1485-1490 http://www.aas.net.cn/CN/abstract/abstract19125.shtml [47] 袁勇, 王飞跃.平行区块链:概念、方法与内涵解析.自动化学报, 2017, 43(10):1703-1712 http://www.aas.net.cn/CN/abstract/abstract19148.shtmlYuan Yong, Wang Fei-Yue. Parallel blockchain:concept, methods and issues. Acta Automatica Sinica, 2017, 43(10):1703-1712 http://www.aas.net.cn/CN/abstract/abstract19148.shtml [48] 麦克卢尔, 斯卡姆布智, 库尔茨[著], 钟向群[译]. 黑客大曝光. 北京: 清华大学出版社, 2010.McClure S, Scambray J, Kurtz G[Author], Zhong Xiang-Qun[Translator]. Hacking Exposed. Beijing: Tsinghua University Press, 2010. [49] 王飞跃.计算实验方法与复杂系统行为分析和决策评估.系统仿真学报, 2015, 16(5):893-897 http://mall.cnki.net/magazine/Article/XTFZ200405008.htmWang Fei-Yue. Computational experiments for behavior analysis and decision evaluation of complex systems. Journal of System Simulation, 2015, 16(5):893-897 http://mall.cnki.net/magazine/Article/XTFZ200405008.htm [50] 王飞跃, 邱晓刚, 曾大军, 曹志冬, 樊宗臣.基于平行系统的非常规突发事件计算实验平台研究.复杂系统与复杂性科学, 2010, 7(4):1-10 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=fzxtyfzxkx201004001Wang Fei-Yue, Qiu Xiao-Gang, Zeng Da-Jun, Cao Zhi-Dong, Fan Zong-Chen. A computational experimental platform for emergency response based on parallel systems. Complex Systems and Complexity Science, 2010, 7(4):1-10 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=fzxtyfzxkx201004001 [51] 崔凯楠, 郑晓龙, 文丁, 赵学亮.计算实验研究方法及应用.自动化学报, 2013, 39(1):1157-1169 http://www.aas.net.cn/CN/abstract/abstract18148.shtmlCui Kai-Nan, Zheng Xiao-Long, Wen Ding, Zhao Xue-Liang. Researches and applications of computational experiments. Acta Automatica Sinica, 2013, 39(1):1157-1169 http://www.aas.net.cn/CN/abstract/abstract18148.shtml [52] 熊刚, 侯家琛, 刘胜, 张家麟, 付满昌.《控制科学与工程学科发展报告》专题报告"核电自动化".北京:中国科学技术出版社, 2011. 176-181Xiong Gang, Hou Jia-Chen, Liu Sheng, Zhang Jia-Lin, Fu Man-Chang. Chapter:Nuclear Power Automation, Report on Advances in Control Science and Engineering, Beijing:ChinaScience & Technology Press.2011. 176-181 [53] Xiong G, Dong X S, Hou J C. Chapter 14:Construction of artificial power systems based on ACP approach. Service Science, Management, and Engineering. Oxford:Elsevier Press and Hangzhou:Zhejiang University Press, 2012. [54] 王飞跃, 刘德荣, 熊刚, 程长建, 赵冬斌.复杂系统的平行控制理论及应用.复杂系统与复杂性科学, 2012, 9(3):1-12 http://mall.cnki.net/magazine/Article/FZXT201203002.htmWang Fei-Yue, Liu De-Rong, Xiong Gang, Cheng Chang-Jian, Zhao Dong-Bin. Parallel control theory of complex systems and applications. Complex Systems and Complexity Science, 2012, 9(3):1-12 http://mall.cnki.net/magazine/Article/FZXT201203002.htm [55] 熊刚, 王飞跃, 侯家琛, 董西松, 张家麟, 付满昌.提高核电站安全可靠性的平行系统方法.系统工程理论与实践, 2012, 32(5):1018-1026 doi: 10.12011/1000-6788(2012)5-1018Gang Xiong, Wang Fei-Yue, Hou Jia-Chen, Dong Xi-Song, Zhang Jia-Lin, Fu Man-Chang. To improve safety and reliability of nuclear power plant with parallel system method. Systems Engineering-Theory and Practice, 2012, 32(5):1018-1026 doi: 10.12011/1000-6788(2012)5-1018 [56] 王丹, 白佳. "和睦系统":中国核电数字化仪控新名片——专访北京广利核系统工程有限公司总经理江国进.中国核电, 2017, 10(3):302-305 http://zghd.cbpt.cnki.net/WKD/WebPublication/wkTextContent.aspx?colType=4&yt=2017&st=03Wang Dan, Bai Jia. FirmSys:a new business card of China's digital I & C system for nuclear power plant——Special interview with JIANG Guojin, Director, China Techenergy Co., Ltd.. China Nuclear Power, 2017, 10(3):302-305 http://zghd.cbpt.cnki.net/WKD/WebPublication/wkTextContent.aspx?colType=4&yt=2017&st=03 期刊类型引用(7)
1. 石保顺,吴一凡,练秋生. 基于无监督学习的编码衍射成像方法研究. 燕山大学学报. 2023(01): 54-63 . 百度学术
2. 王天琪,邢藏菊,肖亮. 一种高分辨率的磁共振成像梯度信号发生器. 现代电子技术. 2023(13): 49-54 . 百度学术
3. 周登文,马路遥,田金月,孙秀秀. 基于特征融合注意网络的图像超分辨率重建. 自动化学报. 2022(09): 2233-2241 . 本站查看
4. 李雨,史娜,孔慧华,雷肖雪. 基于全变分和梯度域卷积稀疏编码的稀疏角度CT重建算法. 激光与光电子学进展. 2021(12): 339-348 . 百度学术
5. 李建武,康杨,周金鹏. PF-FICOTA-SENSE:一种MRI快速重构方法. 自动化学报. 2020(05): 897-908 . 本站查看
6. 周登文,赵丽娟,段然,柴晓亮. 基于递归残差网络的图像超分辨率重建. 自动化学报. 2019(06): 1157-1165 . 本站查看
7. 姚红革,沈新霞,李宇,喻钧,雷松泽. 多模态融合的深度学习脑肿瘤检测方法. 光子学报. 2019(07): 165-176 . 百度学术
其他类型引用(12)
-